15 files changed, 330 insertions, 280 deletions

diff --git a/kernel/cred.c b/kernel/cred.c
index e12c8af793f8..174fa84eca30 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -1,4 +1,4 @@
-/* Task credentials management - see Documentation/credentials.txt
+/* Task credentials management - see Documentation/security/credentials.txt
  *
  * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c09767f7db3e..d863b3c057bb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5028,6 +5028,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
         else
                 perf_event_output(event, nmi, data, regs);
 
+        if (event->fasync && event->pending_kill) {
+                if (nmi) {
+                        event->pending_wakeup = 1;
+                        irq_work_queue(&event->pending);
+                } else
+                        perf_event_wakeup(event);
+        }
+
         return ret;
 }
 
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 74d1c099fbd1..fa27e750dbc0 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -105,9 +105,12 @@ static int __jump_label_text_reserved(struct jump_entry *iter_start,
 }
 
 static void __jump_label_update(struct jump_label_key *key,
-                struct jump_entry *entry, int enable)
+                                struct jump_entry *entry,
+                                struct jump_entry *stop, int enable)
 {
-        for (; entry->key == (jump_label_t)(unsigned long)key; entry++) {
+        for (; (entry < stop) &&
+              (entry->key == (jump_label_t)(unsigned long)key);
+              entry++) {
                 /*
                  * entry->code set to 0 invalidates module init text sections
                  * kernel_text_address() verifies we are not in core kernel
@@ -181,7 +184,11 @@ static void __jump_label_mod_update(struct jump_label_key *key, int enable)
         struct jump_label_mod *mod = key->next;
 
         while (mod) {
-                __jump_label_update(key, mod->entries, enable);
+                struct module *m = mod->mod;
+
+                __jump_label_update(key, mod->entries,
+                                    m->jump_entries + m->num_jump_entries,
+                                    enable);
                 mod = mod->next;
         }
 }
@@ -245,7 +252,8 @@ static int jump_label_add_module(struct module *mod)
                 key->next = jlm;
 
                 if (jump_label_enabled(key))
-                        __jump_label_update(key, iter, JUMP_LABEL_ENABLE);
+                        __jump_label_update(key, iter, iter_stop,
+                                            JUMP_LABEL_ENABLE);
         }
 
         return 0;
@@ -371,7 +379,7 @@ static void jump_label_update(struct jump_label_key *key, int enable)
 
         /* if there are no users, entry can be NULL */
         if (entry)
-                __jump_label_update(key, entry, enable);
+                __jump_label_update(key, entry, __stop___jump_table, enable);
 
 #ifdef CONFIG_MODULES
         __jump_label_mod_update(key, enable);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index beb184689af9..fd8d1e035df9 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -40,6 +40,7 @@
 #include <linux/string.h>
 #include <linux/platform_device.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 
 #include <linux/uaccess.h>
 
@@ -404,24 +405,36 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
                 size_t count, loff_t *f_pos)
 {
         s32 value;
-        int x;
-        char ascii_value[11];
         struct pm_qos_request_list *pm_qos_req;
 
         if (count == sizeof(s32)) {
                 if (copy_from_user(&value, buf, sizeof(s32)))
                         return -EFAULT;
-        } else if (count == 11) { /* len('0x12345678/0') */
-                if (copy_from_user(ascii_value, buf, 11))
+        } else if (count <= 11) { /* ASCII perhaps? */
+                char ascii_value[11];
+                unsigned long int ulval;
+                int ret;
+
+                if (copy_from_user(ascii_value, buf, count))
                         return -EFAULT;
-                if (strlen(ascii_value) != 10)
-                        return -EINVAL;
-                x = sscanf(ascii_value, "%x", &value);
-                if (x != 1)
+
+                if (count > 10) {
+                        if (ascii_value[10] == '\n')
+                                ascii_value[10] = '\0';
+                        else
+                                return -EINVAL;
+                } else {
+                        ascii_value[count] = '\0';
+                }
+                ret = strict_strtoul(ascii_value, 16, &ulval);
+                if (ret) {
+                        pr_debug("%s, 0x%lx, 0x%x\n", ascii_value, ulval, ret);
                         return -EINVAL;
-                pr_debug("%s, %d, 0x%x\n", ascii_value, x, value);
-        } else
+                }
+                value = (s32)lower_32_bits(ulval);
+        } else {
                 return -EINVAL;
+        }
 
         pm_qos_req = filp->private_data;
         pm_qos_update_request(pm_qos_req, value);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f9bec56d8825..8f7b1db1ece1 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -25,7 +25,6 @@
 #include <linux/gfp.h>
 #include <linux/syscore_ops.h>
 #include <scsi/scsi_scan.h>
-#include <asm/suspend.h>
 
 #include "power.h"
 
@@ -55,10 +54,9 @@ static int hibernation_mode = HIBERNATION_SHUTDOWN;
 static const struct platform_hibernation_ops *hibernation_ops;
 
 /**
- * hibernation_set_ops - set the global hibernate operations
- * @ops: the hibernation operations to use in subsequent hibernation transitions
+ * hibernation_set_ops - Set the global hibernate operations.
+ * @ops: Hibernation operations to use in subsequent hibernation transitions.
  */
-
 void hibernation_set_ops(const struct platform_hibernation_ops *ops)
 {
         if (ops && !(ops->begin && ops->end &&  ops->pre_snapshot
@@ -115,10 +113,9 @@ static int hibernation_test(int level) { return 0; }
 #endif /* !CONFIG_PM_DEBUG */
 
 /**
- *      platform_begin - tell the platform driver that we're starting
- *      hibernation
+ * platform_begin - Call platform to start hibernation.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static int platform_begin(int platform_mode)
 {
         return (platform_mode && hibernation_ops) ?
@@ -126,10 +123,9 @@ static int platform_begin(int platform_mode)
 }
 
 /**
- *      platform_end - tell the platform driver that we've entered the
- *      working state
+ * platform_end - Call platform to finish transition to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static void platform_end(int platform_mode)
 {
         if (platform_mode && hibernation_ops)
@@ -137,8 +133,11 @@ static void platform_end(int platform_mode)
 }
 
 /**
- *      platform_pre_snapshot - prepare the machine for hibernation using the
- *      platform driver if so configured and return an error code if it fails
+ * platform_pre_snapshot - Call platform to prepare the machine for hibernation.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to prepare the system for creating a hibernate image,
+ * if so configured, and return an error code if that fails.
  */
 
 static int platform_pre_snapshot(int platform_mode)
@@ -148,10 +147,14 @@ static int platform_pre_snapshot(int platform_mode)
 }
 
 /**
- *      platform_leave - prepare the machine for switching to the normal mode
- *      of operation using the platform driver (called with interrupts disabled)
+ * platform_leave - Call platform to prepare a transition to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver prepare to prepare the machine for switching to the
+ * normal mode of operation.
+ *
+ * This routine is called on one CPU with interrupts disabled.
  */
-
 static void platform_leave(int platform_mode)
 {
         if (platform_mode && hibernation_ops)
@@ -159,10 +162,14 @@ static void platform_leave(int platform_mode)
 }
 
 /**
- *      platform_finish - switch the machine to the normal mode of operation
- *      using the platform driver (must be called after platform_prepare())
+ * platform_finish - Call platform to switch the system to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to switch the machine to the normal mode of
+ * operation.
+ *
+ * This routine must be called after platform_prepare().
  */
-
 static void platform_finish(int platform_mode)
 {
         if (platform_mode && hibernation_ops)
@@ -170,11 +177,15 @@ static void platform_finish(int platform_mode)
 }
 
 /**
- *      platform_pre_restore - prepare the platform for the restoration from a
- *      hibernation image.  If the restore fails after this function has been
- *      called, platform_restore_cleanup() must be called.
+ * platform_pre_restore - Prepare for hibernate image restoration.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to prepare the system for resume from a hibernation
+ * image.
+ *
+ * If the restore fails after this function has been called,
+ * platform_restore_cleanup() must be called.
  */
-
 static int platform_pre_restore(int platform_mode)
 {
         return (platform_mode && hibernation_ops) ?
@@ -182,12 +193,16 @@ static int platform_pre_restore(int platform_mode)
 }
 
 /**
- *      platform_restore_cleanup - switch the platform to the normal mode of
- *      operation after a failing restore.  If platform_pre_restore() has been
- *      called before the failing restore, this function must be called too,
- *      regardless of the result of platform_pre_restore().
+ * platform_restore_cleanup - Switch to the working state after failing restore.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to switch the system to the normal mode of operation
+ * after a failing restore.
+ *
+ * If platform_pre_restore() has been called before the failing restore, this
+ * function must be called too, regardless of the result of
+ * platform_pre_restore().
  */
-
 static void platform_restore_cleanup(int platform_mode)
 {
         if (platform_mode && hibernation_ops)
@@ -195,10 +210,9 @@ static void platform_restore_cleanup(int platform_mode)
 }
 
 /**
- *      platform_recover - recover the platform from a failure to suspend
- *      devices.
+ * platform_recover - Recover from a failure to suspend devices.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static void platform_recover(int platform_mode)
 {
         if (platform_mode && hibernation_ops && hibernation_ops->recover)
@@ -206,13 +220,12 @@ static void platform_recover(int platform_mode)
 }
 
 /**
- *      swsusp_show_speed - print the time elapsed between two events.
- *      @start: Starting event.
- *      @stop: Final event.
- *      @nr_pages -     number of pages processed between @start and @stop
- *      @msg -          introductory message to print
+ * swsusp_show_speed - Print time elapsed between two events during hibernation.
+ * @start: Starting event.
+ * @stop: Final event.
+ * @nr_pages: Number of memory pages processed between @start and @stop.
+ * @msg: Additional diagnostic message to print.
  */
-
 void swsusp_show_speed(struct timeval *start, struct timeval *stop,
                         unsigned nr_pages, char *msg)
 {
@@ -235,25 +248,18 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
 }
 
 /**
- *      create_image - freeze devices that need to be frozen with interrupts
- *      off, create the hibernation image and thaw those devices.  Control
- *      reappears in this routine after a restore.
+ * create_image - Create a hibernation image.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Execute device drivers' .freeze_noirq() callbacks, create a hibernation image
+ * and execute the drivers' .thaw_noirq() callbacks.
+ *
+ * Control reappears in this routine after the subsequent restore.
  */
-
 static int create_image(int platform_mode)
 {
         int error;
 
-        error = arch_prepare_suspend();
-        if (error)
-                return error;
-
-        /* At this point, dpm_suspend_start() has been called, but *not*
-         * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now.
-         * Otherwise, drivers for some devices (e.g. interrupt controllers)
-         * become desynchronized with the actual state of the hardware
-         * at resume time, and evil weirdness ensues.
-         */
         error = dpm_suspend_noirq(PMSG_FREEZE);
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to power down, "
@@ -297,9 +303,6 @@ static int create_image(int platform_mode)
 
  Power_up:
         syscore_resume();
-        /* NOTE:  dpm_resume_noirq() is just a resume() for devices
-         * that suspended with irqs off ... no overall powerup.
-         */
 
  Enable_irqs:
         local_irq_enable();
@@ -317,14 +320,11 @@ static int create_image(int platform_mode)
 }
 
 /**
- *      hibernation_snapshot - quiesce devices and create the hibernation
- *      snapshot image.
- *      @platform_mode - if set, use the platform driver, if available, to
- *                       prepare the platform firmware for the power transition.
+ * hibernation_snapshot - Quiesce devices and create a hibernation image.
+ * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- *      Must be called with pm_mutex held
+ * This routine must be called with pm_mutex held.
  */
-
 int hibernation_snapshot(int platform_mode)
 {
         pm_message_t msg = PMSG_RECOVER;
@@ -384,13 +384,14 @@ int hibernation_snapshot(int platform_mode)
 }
 
 /**
- *      resume_target_kernel - prepare devices that need to be suspended with
- *      interrupts off, restore the contents of highmem that have not been
- *      restored yet from the image and run the low level code that will restore
- *      the remaining contents of memory and switch to the just restored target
- *      kernel.
+ * resume_target_kernel - Restore system state from a hibernation image.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Execute device drivers' .freeze_noirq() callbacks, restore the contents of
+ * highmem that have not been restored yet from the image and run the low-level
+ * code that will restore the remaining contents of memory and switch to the
+ * just restored target kernel.
  */
-
 static int resume_target_kernel(bool platform_mode)
 {
         int error;
@@ -416,24 +417,26 @@ static int resume_target_kernel(bool platform_mode)
         if (error)
                 goto Enable_irqs;
 
-        /* We'll ignore saved state, but this gets preempt count (etc) right */
         save_processor_state();
         error = restore_highmem();
         if (!error) {
                 error = swsusp_arch_resume();
                 /*
                  * The code below is only ever reached in case of a failure.
-                 * Otherwise execution continues at place where
-                 * swsusp_arch_suspend() was called
+                 * Otherwise, execution continues at the place where
+                 * swsusp_arch_suspend() was called.
                  */
                 BUG_ON(!error);
-                /* This call to restore_highmem() undos the previous one */
+                /*
+                 * This call to restore_highmem() reverts the changes made by
+                 * the previous one.
+                 */
                 restore_highmem();
         }
         /*
          * The only reason why swsusp_arch_resume() can fail is memory being
          * very tight, so we have to free it as soon as we can to avoid
-         * subsequent failures
+         * subsequent failures.
          */
         swsusp_free();
         restore_processor_state();
@@ -456,14 +459,12 @@ static int resume_target_kernel(bool platform_mode)
 }
 
 /**
- *      hibernation_restore - quiesce devices and restore the hibernation
- *      snapshot image.  If successful, control returns in hibernation_snaphot()
- *      @platform_mode - if set, use the platform driver, if available, to
- *                       prepare the platform firmware for the transition.
+ * hibernation_restore - Quiesce devices and restore from a hibernation image.
+ * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- *      Must be called with pm_mutex held
+ * This routine must be called with pm_mutex held.  If it is successful, control
+ * reappears in the restored target kernel in hibernation_snaphot().
  */
-
 int hibernation_restore(int platform_mode)
 {
         int error;
@@ -483,10 +484,8 @@ int hibernation_restore(int platform_mode)
 }
 
 /**
- *      hibernation_platform_enter - enter the hibernation state using the
- *      platform driver (if available)
+ * hibernation_platform_enter - Power off the system using the platform driver.
  */
-
 int hibernation_platform_enter(void)
 {
         int error;
@@ -557,12 +556,12 @@ int hibernation_platform_enter(void)
 }
 
 /**
- *      power_down - Shut the machine down for hibernation.
+ * power_down - Shut the machine down for hibernation.
  *
- *      Use the platform driver, if configured so; otherwise try
- *      to power off or reboot.
+ * Use the platform driver, if configured, to put the system into the sleep
+ * state corresponding to hibernation, or try to power it off or reboot,
+ * depending on the value of hibernation_mode.
  */
-
 static void power_down(void)
 {
         switch (hibernation_mode) {
@@ -599,9 +598,8 @@ static int prepare_processes(void)
 }
 
 /**
- *      hibernate - The granpappy of the built-in hibernation management
+ * hibernate - Carry out system hibernation, including saving the image.
  */
-
 int hibernate(void)
 {
         int error;
@@ -679,17 +677,20 @@ int hibernate(void)
 
 
 /**
- *      software_resume - Resume from a saved image.
+ * software_resume - Resume from a saved hibernation image.
  *
- *      Called as a late_initcall (so all devices are discovered and
- *      initialized), we call swsusp to see if we have a saved image or not.
- *      If so, we quiesce devices, the restore the saved image. We will
- *      return above (in hibernate() ) if everything goes well.
- *      Otherwise, we fail gracefully and return to the normally
- *      scheduled program.
+ * This routine is called as a late initcall, when all devices have been
+ * discovered and initialized already.
  *
+ * The image reading code is called to see if there is a hibernation image
+ * available for reading.  If that is the case, devices are quiesced and the
+ * contents of memory is restored from the saved image.
+ *
+ * If this is successful, control reappears in the restored target kernel in
+ * hibernation_snaphot() which returns to hibernate().  Otherwise, the routine
+ * attempts to recover gracefully and make the kernel return to the normal mode
+ * of operation.
  */
-
 static int software_resume(void)
 {
         int error;
@@ -819,21 +820,17 @@ static const char * const hibernation_modes[] = {
         [HIBERNATION_TESTPROC]  = "testproc",
 };
 
-/**
- *      disk - Control hibernation mode
- *
- *      Suspend-to-disk can be handled in several ways. We have a few options
- *      for putting the system to sleep - using the platform driver (e.g. ACPI
- *      or other hibernation_ops), powering off the system or rebooting the
- *      system (for testing) as well as the two test modes.
+/*
+ * /sys/power/disk - Control hibernation mode.
  *
- *      The system can support 'platform', and that is known a priori (and
- *      encoded by the presence of hibernation_ops). However, the user may
- *      choose 'shutdown' or 'reboot' as alternatives, as well as one fo the
- *      test modes, 'test' or 'testproc'.
+ * Hibernation can be handled in several ways.  There are a few different ways
+ * to put the system into the sleep state: using the platform driver (e.g. ACPI
+ * or other hibernation_ops), powering it off or rebooting it (for testing
+ * mostly), or using one of the two available test modes.
  *
- *      show() will display what the mode is currently set to.
- *      store() will accept one of
+ * The sysfs file /sys/power/disk provides an interface for selecting the
+ * hibernation mode to use.  Reading from this file causes the available modes
+ * to be printed.  There are 5 modes that can be supported:
  *
  *      'platform'
  *      'shutdown'
@@ -841,8 +838,14 @@ static const char * const hibernation_modes[] = {
  *      'test'
  *      'testproc'
  *
- *      It will only change to 'platform' if the system
- *      supports it (as determined by having hibernation_ops).
+ * If a platform hibernation driver is in use, 'platform' will be supported
+ * and will be used by default.  Otherwise, 'shutdown' will be used by default.
+ * The selected option (i.e. the one corresponding to the current value of
+ * hibernation_mode) is enclosed by a square bracket.
+ *
+ * To select a given hibernation mode it is necessary to write the mode's
+ * string representation (as returned by reading from /sys/power/disk) back
+ * into /sys/power/disk.
  */
 
 static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -875,7 +878,6 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
         return buf-start;
 }
 
-
 static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
                           const char *buf, size_t n)
 {
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f07d2f03181a..77a7671dd147 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -36,7 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>
@@ -95,7 +95,6 @@ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
 
@@ -163,7 +162,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
         .dynticks_nesting = 1,
-        .dynticks = 1,
+        .dynticks = ATOMIC_INIT(1),
 };
 #endif /* #ifdef CONFIG_NO_HZ */
 
@@ -322,13 +321,25 @@ void rcu_enter_nohz(void)
         unsigned long flags;
         struct rcu_dynticks *rdtp;
 
-        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
         local_irq_save(flags);
         rdtp = &__get_cpu_var(rcu_dynticks);
-        rdtp->dynticks++;
-        rdtp->dynticks_nesting--;
-        WARN_ON_ONCE(rdtp->dynticks & 0x1);
+        if (--rdtp->dynticks_nesting) {
+                local_irq_restore(flags);
+                return;
+        }
+        /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+        smp_mb__before_atomic_inc();  /* See above. */
+        atomic_inc(&rdtp->dynticks);
+        smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+        WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
         local_irq_restore(flags);
+
+        /* If the interrupt queued a callback, get out of dyntick mode. */
+        if (in_irq() &&
+            (__get_cpu_var(rcu_sched_data).nxtlist ||
+             __get_cpu_var(rcu_bh_data).nxtlist ||
+             rcu_preempt_needs_cpu(smp_processor_id())))
+                set_need_resched();
 }
 
 /*
@@ -344,11 +355,16 @@ void rcu_exit_nohz(void)
 
         local_irq_save(flags);
         rdtp = &__get_cpu_var(rcu_dynticks);
-        rdtp->dynticks++;
-        rdtp->dynticks_nesting++;
-        WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
+        if (rdtp->dynticks_nesting++) {
+                local_irq_restore(flags);
+                return;
+        }
+        smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
+        atomic_inc(&rdtp->dynticks);
+        /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+        smp_mb__after_atomic_inc();  /* See above. */
+        WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
         local_irq_restore(flags);
-        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
 /**
@@ -362,11 +378,15 @@ void rcu_nmi_enter(void)
 {
         struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-        if (rdtp->dynticks & 0x1)
+        if (rdtp->dynticks_nmi_nesting == 0 &&
+            (atomic_read(&rdtp->dynticks) & 0x1))
                 return;
-        rdtp->dynticks_nmi++;
-        WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
-        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+        rdtp->dynticks_nmi_nesting++;
+        smp_mb__before_atomic_inc();  /* Force delay from prior write. */
+        atomic_inc(&rdtp->dynticks);
+        /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+        smp_mb__after_atomic_inc();  /* See above. */
+        WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 }
 
 /**
@@ -380,11 +400,14 @@ void rcu_nmi_exit(void)
 {
         struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-        if (rdtp->dynticks & 0x1)
+        if (rdtp->dynticks_nmi_nesting == 0 ||
+            --rdtp->dynticks_nmi_nesting != 0)
                 return;
-        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-        rdtp->dynticks_nmi++;
-        WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
+        /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+        smp_mb__before_atomic_inc();  /* See above. */
+        atomic_inc(&rdtp->dynticks);
+        smp_mb__after_atomic_inc();  /* Force delay to next write. */
+        WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
 /**
@@ -395,13 +418,7 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_enter(void)
 {
-        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-        if (rdtp->dynticks_nesting++)
-                return;
-        rdtp->dynticks++;
-        WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
-        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+        rcu_exit_nohz();
 }
 
 /**
@@ -413,18 +430,7 @@ void rcu_irq_enter(void)
  */
 void rcu_irq_exit(void)
 {
-        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-        if (--rdtp->dynticks_nesting)
-                return;
-        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-        rdtp->dynticks++;
-        WARN_ON_ONCE(rdtp->dynticks & 0x1);
-
-        /* If the interrupt queued a callback, get out of dyntick mode. */
-        if (__this_cpu_read(rcu_sched_data.nxtlist) ||
-            __this_cpu_read(rcu_bh_data.nxtlist))
-                set_need_resched();
+        rcu_enter_nohz();
 }
 
 #ifdef CONFIG_SMP
@@ -436,19 +442,8 @@ void rcu_irq_exit(void)
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
-        int ret;
-        int snap;
-        int snap_nmi;
-
-        snap = rdp->dynticks->dynticks;
-        snap_nmi = rdp->dynticks->dynticks_nmi;
-        smp_mb();       /* Order sampling of snap with end of grace period. */
-        rdp->dynticks_snap = snap;
-        rdp->dynticks_nmi_snap = snap_nmi;
-        ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
-        if (ret)
-                rdp->dynticks_fqs++;
-        return ret;
+        rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+        return 0;
 }
 
 /*
@@ -459,16 +454,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-        long curr;
-        long curr_nmi;
-        long snap;
-        long snap_nmi;
+        unsigned long curr;
+        unsigned long snap;
 
-        curr = rdp->dynticks->dynticks;
-        snap = rdp->dynticks_snap;
-        curr_nmi = rdp->dynticks->dynticks_nmi;
-        snap_nmi = rdp->dynticks_nmi_snap;
-        smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+        curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
+        snap = (unsigned long)rdp->dynticks_snap;
 
         /*
          * If the CPU passed through or entered a dynticks idle phase with
@@ -478,8 +468,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
          * read-side critical section that started before the beginning
          * of the current RCU grace period.
          */
-        if ((curr != snap || (curr & 0x1) == 0) &&
-            (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+        if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
                 rdp->dynticks_fqs++;
                 return 1;
         }
@@ -908,6 +897,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
         unsigned long gp_duration;
 
         WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+
+        /*
+         * Ensure that all grace-period and pre-grace-period activity
+         * is seen before the assignment to rsp->completed.
+         */
+        smp_mb(); /* See above block comment. */
         gp_duration = jiffies - rsp->gp_start;
         if (gp_duration > rsp->gp_max)
                 rsp->gp_max = gp_duration;
@@ -1455,25 +1450,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_process_callbacks(void)
 {
-        /*
-         * Memory references from any prior RCU read-side critical sections
-         * executed by the interrupted code must be seen before any RCU
-         * grace-period manipulations below.
-         */
-        smp_mb(); /* See above block comment. */
-
         __rcu_process_callbacks(&rcu_sched_state,
                                 &__get_cpu_var(rcu_sched_data));
         __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
         rcu_preempt_process_callbacks();
 
-        /*
-         * Memory references from any later RCU read-side critical sections
-         * executed by the interrupted code must be seen after any RCU
-         * grace-period manipulations above.
-         */
-        smp_mb(); /* See above block comment. */
-
         /* If we are last CPU on way to dyntick-idle mode, accelerate it. */
         rcu_needs_cpu_flush();
 }
@@ -1494,7 +1475,7 @@ static void invoke_rcu_cpu_kthread(void)
                 local_irq_restore(flags);
                 return;
         }
-        wake_up(&__get_cpu_var(rcu_cpu_wq));
+        wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
         local_irq_restore(flags);
 }
 
@@ -1544,13 +1525,10 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
  */
 static void rcu_cpu_kthread_timer(unsigned long arg)
 {
-        unsigned long flags;
         struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
         struct rcu_node *rnp = rdp->mynode;
 
-        raw_spin_lock_irqsave(&rnp->lock, flags);
-        rnp->wakemask |= rdp->grpmask;
-        raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        atomic_or(rdp->grpmask, &rnp->wakemask);
         invoke_rcu_node_kthread(rnp);
 }
 
@@ -1617,14 +1595,12 @@ static int rcu_cpu_kthread(void *arg)
         unsigned long flags;
         int spincnt = 0;
         unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-        wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu);
         char work;
         char *workp = &per_cpu(rcu_cpu_has_work, cpu);
 
         for (;;) {
                 *statusp = RCU_KTHREAD_WAITING;
-                wait_event_interruptible(*wqp,
-                                         *workp != 0 || kthread_should_stop());
+                rcu_wait(*workp != 0 || kthread_should_stop());
                 local_bh_disable();
                 if (rcu_cpu_kthread_should_stop(cpu)) {
                         local_bh_enable();
@@ -1672,10 +1648,10 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
         if (IS_ERR(t))
                 return PTR_ERR(t);
         kthread_bind(t, cpu);
+        set_task_state(t, TASK_INTERRUPTIBLE);
         per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
         WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
         per_cpu(rcu_cpu_kthread_task, cpu) = t;
-        wake_up_process(t);
         sp.sched_priority = RCU_KTHREAD_PRIO;
         sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         return 0;
@@ -1698,11 +1674,10 @@ static int rcu_node_kthread(void *arg)
 
         for (;;) {
                 rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-                wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0);
+                rcu_wait(atomic_read(&rnp->wakemask) != 0);
                 rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
                 raw_spin_lock_irqsave(&rnp->lock, flags);
-                mask = rnp->wakemask;
-                rnp->wakemask = 0;
+                mask = atomic_xchg(&rnp->wakemask, 0);
                 rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
                 for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
                         if ((mask & 0x1) == 0)
@@ -1781,9 +1756,9 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
                 if (IS_ERR(t))
                         return PTR_ERR(t);
                 raw_spin_lock_irqsave(&rnp->lock, flags);
+                set_task_state(t, TASK_INTERRUPTIBLE);
                 rnp->node_kthread_task = t;
                 raw_spin_unlock_irqrestore(&rnp->lock, flags);
-                wake_up_process(t);
                 sp.sched_priority = 99;
                 sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         }
@@ -1800,21 +1775,16 @@ static int __init rcu_spawn_kthreads(void)
 
         rcu_kthreads_spawnable = 1;
         for_each_possible_cpu(cpu) {
-                init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu));
                 per_cpu(rcu_cpu_has_work, cpu) = 0;
                 if (cpu_online(cpu))
                         (void)rcu_spawn_one_cpu_kthread(cpu);
         }
         rnp = rcu_get_root(rcu_state);
-        init_waitqueue_head(&rnp->node_wq);
-        rcu_init_boost_waitqueue(rnp);
         (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-        if (NUM_RCU_NODES > 1)
-                rcu_for_each_leaf_node(rcu_state, rnp) {
-                        init_waitqueue_head(&rnp->node_wq);
-                        rcu_init_boost_waitqueue(rnp);
+        if (NUM_RCU_NODES > 1) {
+                rcu_for_each_leaf_node(rcu_state, rnp)
                         (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-                }
+        }
         return 0;
 }
 early_initcall(rcu_spawn_kthreads);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 257664815d5d..7b9a08b4aaea 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,11 +84,9 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-        int dynticks_nesting;   /* Track nesting level, sort of. */
-        int dynticks;           /* Even value for dynticks-idle, else odd. */
-        int dynticks_nmi;       /* Even value for either dynticks-idle or */
-                                /*  not in nmi handler, else odd.  So this */
-                                /*  remains even for nmi from irq handler. */
+        int dynticks_nesting;   /* Track irq/process nesting level. */
+        int dynticks_nmi_nesting; /* Track NMI nesting level. */
+        atomic_t dynticks;      /* Even value for dynticks-idle, else odd. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -121,7 +119,9 @@ struct rcu_node {
                                 /*  elements that need to drain to allow the */
                                 /*  current expedited grace period to */
                                 /*  complete (only for TREE_PREEMPT_RCU). */
-        unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
+        atomic_t wakemask;      /* CPUs whose kthread needs to be awakened. */
+                                /*  Since this has meaning only for leaf */
+                                /*  rcu_node structures, 32 bits suffices. */
         unsigned long qsmaskinit;
                                 /* Per-GP initial value for qsmask & expmask. */
         unsigned long grpmask;  /* Mask to apply to parent qsmask. */
@@ -159,9 +159,6 @@ struct rcu_node {
         struct task_struct *boost_kthread_task;
                                 /* kthread that takes care of priority */
                                 /*  boosting for this rcu_node structure. */
-        wait_queue_head_t boost_wq;
-                                /* Wait queue on which to park the boost */
-                                /*  kthread. */
         unsigned int boost_kthread_status;
                                 /* State of boost_kthread_task for tracing. */
         unsigned long n_tasks_boosted;
@@ -188,9 +185,6 @@ struct rcu_node {
                                 /* kthread that takes care of this rcu_node */
                                 /*  structure, for example, awakening the */
                                 /*  per-CPU kthreads as needed. */
-        wait_queue_head_t node_wq;
-                                /* Wait queue on which to park the per-node */
-                                /*  kthread. */
         unsigned int node_kthread_status;
                                 /* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
@@ -284,7 +278,6 @@ struct rcu_data {
         /* 3) dynticks interface. */
         struct rcu_dynticks *dynticks;  /* Shared per-CPU dynticks state. */
         int dynticks_snap;              /* Per-GP tracking for dynticks. */
-        int dynticks_nmi_snap;          /* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
         /* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -337,6 +330,16 @@ struct rcu_data {
                                                 /*  scheduling clock irq */
                                                 /*  before ratting on them. */
 
+#define rcu_wait(cond)                                                  \
+do {                                                                    \
+        for (;;) {                                                      \
+                set_current_state(TASK_INTERRUPTIBLE);                  \
+                if (cond)                                               \
+                        break;                                          \
+                schedule();                                             \
+        }                                                               \
+        __set_current_state(TASK_RUNNING);                              \
+} while (0)
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -446,7 +449,6 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
                                           cpumask_var_t cm);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3f6559a5f5cd..a767b7dac365 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1196,8 +1196,7 @@ static int rcu_boost_kthread(void *arg)
 
         for (;;) {
                 rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
-                wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
-                                                        rnp->exp_tasks);
+                rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
                 rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
                 more2boost = rcu_boost(rnp);
                 if (more2boost)
@@ -1275,14 +1274,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 }
 
 /*
- * Initialize the RCU-boost waitqueue.
- */
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-        init_waitqueue_head(&rnp->boost_wq);
-}
-
-/*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
  * Returns zero if all is well, a negated errno otherwise.
@@ -1304,9 +1295,9 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
         if (IS_ERR(t))
                 return PTR_ERR(t);
         raw_spin_lock_irqsave(&rnp->lock, flags);
+        set_task_state(t, TASK_INTERRUPTIBLE);
         rnp->boost_kthread_task = t;
         raw_spin_unlock_irqrestore(&rnp->lock, flags);
-        wake_up_process(t);
         sp.sched_priority = RCU_KTHREAD_PRIO;
         sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         return 0;
@@ -1328,10 +1319,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-}
-
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
                                                  struct rcu_node *rnp,
                                                  int rnp_index)
@@ -1520,7 +1507,6 @@ int rcu_needs_cpu(int cpu)
 {
         int c = 0;
         int snap;
-        int snap_nmi;
         int thatcpu;
 
         /* Check for being in the holdoff period. */
@@ -1531,10 +1517,10 @@ int rcu_needs_cpu(int cpu)
         for_each_online_cpu(thatcpu) {
                 if (thatcpu == cpu)
                         continue;
-                snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-                snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+                snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+                                                     thatcpu).dynticks);
                 smp_mb(); /* Order sampling of snap with end of grace period. */
-                if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+                if ((snap & 0x1) != 0) {
                         per_cpu(rcu_dyntick_drain, cpu) = 0;
                         per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
                         return rcu_needs_cpu_quick_check(cpu);
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index aa0fd72b4bc7..9678cc3650f5 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -69,10 +69,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
                    rdp->passed_quiesc, rdp->passed_quiesc_completed,
                    rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
-        seq_printf(m, " dt=%d/%d dn=%d df=%lu",
-                   rdp->dynticks->dynticks,
+        seq_printf(m, " dt=%d/%d/%d df=%lu",
+                   atomic_read(&rdp->dynticks->dynticks),
                    rdp->dynticks->dynticks_nesting,
-                   rdp->dynticks->dynticks_nmi,
+                   rdp->dynticks->dynticks_nmi_nesting,
                    rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -141,9 +141,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
                    rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
         seq_printf(m, ",%d,%d,%d,%lu",
-                   rdp->dynticks->dynticks,
+                   atomic_read(&rdp->dynticks->dynticks),
                    rdp->dynticks->dynticks_nesting,
-                   rdp->dynticks->dynticks_nmi,
+                   rdp->dynticks->dynticks_nmi_nesting,
                    rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -167,7 +167,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
         seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
-        seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+        seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d017c2c82c44..1ee417fcbfa5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -109,12 +109,18 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 static void ftrace_global_list_func(unsigned long ip,
                                     unsigned long parent_ip)
 {
-        struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/
+        struct ftrace_ops *op;
+
+        if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
+                return;
 
+        trace_recursion_set(TRACE_GLOBAL_BIT);
+        op = rcu_dereference_raw(ftrace_global_list); /*see above*/
         while (op != &ftrace_list_end) {
                 op->func(ip, parent_ip);
                 op = rcu_dereference_raw(op->next); /*see above*/
         };
+        trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
@@ -1638,12 +1644,12 @@ static void ftrace_startup_enable(int command)
         ftrace_run_update_code(command);
 }
 
-static void ftrace_startup(struct ftrace_ops *ops, int command)
+static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
         bool hash_enable = true;
 
         if (unlikely(ftrace_disabled))
-                return;
+                return -ENODEV;
 
         ftrace_start_up++;
         command |= FTRACE_ENABLE_CALLS;
@@ -1662,6 +1668,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command)
                 ftrace_hash_rec_enable(ops, 1);
 
         ftrace_startup_enable(command);
+
+        return 0;
 }
 
 static void ftrace_shutdown(struct ftrace_ops *ops, int command)
@@ -2501,7 +2509,7 @@ static void __enable_ftrace_function_probe(void)
 
         ret = __register_ftrace_function(&trace_probe_ops);
         if (!ret)
-                ftrace_startup(&trace_probe_ops, 0);
+                ret = ftrace_startup(&trace_probe_ops, 0);
 
         ftrace_probe_registered = 1;
 }
@@ -3466,7 +3474,11 @@ device_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)   do { } while (0)
+# define ftrace_startup(ops, command)                   \
+        ({                                              \
+                (ops)->flags |= FTRACE_OPS_FL_ENABLED;  \
+                0;                                      \
+        })
 # define ftrace_shutdown(ops, command)  do { } while (0)
 # define ftrace_startup_sysctl()        do { } while (0)
 # define ftrace_shutdown_sysctl()       do { } while (0)
@@ -3484,6 +3496,10 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
         struct ftrace_ops *op;
 
+        if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
+                return;
+
+        trace_recursion_set(TRACE_INTERNAL_BIT);
         /*
          * Some of the ops may be dynamically allocated,
          * they must be freed after a synchronize_sched().
@@ -3496,6 +3512,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
                 op = rcu_dereference_raw(op->next);
         };
         preempt_enable_notrace();
+        trace_recursion_clear(TRACE_INTERNAL_BIT);
 }
 
 static void clear_ftrace_swapper(void)
@@ -3799,7 +3816,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
         ret = __register_ftrace_function(ops);
         if (!ret)
-                ftrace_startup(ops, 0);
+                ret = ftrace_startup(ops, 0);
 
 
  out_unlock:
@@ -4045,7 +4062,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
         ftrace_graph_return = retfunc;
         ftrace_graph_entry = entryfunc;
 
-        ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+        ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
         mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0ef7b4b2a1f7..b0c7aa407943 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2216,7 +2216,7 @@ static noinline void trace_recursive_fail(void)
 
         printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
                     "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-                    current->trace_recursion,
+                    trace_recursion_buffer(),
                     hardirq_count() >> HARDIRQ_SHIFT,
                     softirq_count() >> SOFTIRQ_SHIFT,
                     in_nmi());
@@ -2226,9 +2226,9 @@ static noinline void trace_recursive_fail(void)
 
 static inline int trace_recursive_lock(void)
 {
-        current->trace_recursion++;
+        trace_recursion_inc();
 
-        if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+        if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
                 return 0;
 
         trace_recursive_fail();
@@ -2238,9 +2238,9 @@ static inline int trace_recursive_lock(void)
 
 static inline void trace_recursive_unlock(void)
 {
-        WARN_ON_ONCE(!current->trace_recursion);
+        WARN_ON_ONCE(!trace_recursion_buffer());
 
-        current->trace_recursion--;
+        trace_recursion_dec();
 }
 
 #else
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b69c4bd306f..229f8591f61d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -784,4 +784,19 @@ extern const char *__stop___trace_bprintk_fmt[];
         FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT              (1<<11)
+#define TRACE_GLOBAL_BIT                (1<<12)
+
+#define trace_recursion_set(bit)        do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)      do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)       ((current)->trace_recursion & (bit))
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 2fe110341359..686ec399f2a8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1657,7 +1657,12 @@ static struct ftrace_ops trace_ops __initdata  =
 
 static __init void event_trace_self_test_with_function(void)
 {
-        register_ftrace_function(&trace_ops);
+        int ret;
+        ret = register_ftrace_function(&trace_ops);
+        if (WARN_ON(ret < 0)) {
+                pr_info("Failed to enable function tracer for event tests\n");
+                return;
+        }
         pr_info("Running tests again, along with the function tracer\n");
         event_trace_self_tests();
         unregister_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cf535ccedc86..e37de492a9e1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -353,6 +353,33 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
+#if BITS_PER_LONG == 32
+const char *
+ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
+                         const struct trace_print_flags_u64 *symbol_array)
+{
+        int i;
+        const char *ret = p->buffer + p->len;
+
+        for (i = 0;  symbol_array[i].name; i++) {
+
+                if (val != symbol_array[i].mask)
+                        continue;
+
+                trace_seq_puts(p, symbol_array[i].name);
+                break;
+        }
+
+        if (!p->len)
+                trace_seq_printf(p, "0x%llx", val);
+
+        trace_seq_putc(p, 0);
+
+        return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq_u64);
+#endif
+
 const char *
 ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7daa4b072e9f..3d0c56ad4792 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -415,15 +415,13 @@ static void watchdog_nmi_disable(int cpu) { return; }
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /* prepare/enable/disable routines */
-static int watchdog_prepare_cpu(int cpu)
+static void watchdog_prepare_cpu(int cpu)
 {
         struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
 
         WARN_ON(per_cpu(softlockup_watchdog, cpu));
         hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         hrtimer->function = watchdog_timer_fn;
-
-        return 0;
 }
 
 static int watchdog_enable(int cpu)
@@ -542,17 +540,16 @@ static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
         int hotcpu = (unsigned long)hcpu;
-        int err = 0;
 
         switch (action) {
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                err = watchdog_prepare_cpu(hotcpu);
+                watchdog_prepare_cpu(hotcpu);
                 break;
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 if (watchdog_enabled)
-                        err = watchdog_enable(hotcpu);
+                        watchdog_enable(hotcpu);
                 break;
 #ifdef CONFIG_HOTPLUG_CPU
         case CPU_UP_CANCELED: